Audio signal processing device and audio signal processing method

Abstract

To provide a voice signal processing device and a voice signal processing method that can make it harder for a passenger to hear a transmitted voice in a cabin without hindering a temporary conversation between a caller and the passenger in the cabin.SOLUTION: A voice signal processing device according to one embodiment is configured to output a sound, making it harder for a passenger other than a caller in a cabin to hear a call voice of the caller in the cabin, to the passenger through a speaker. The voice signal processing device is configured to stop outputting the sound when detecting utterance from the caller to the passenger or from the passenger to the caller during the call.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The disclosed embodiments relate to an audio signal processing apparatus and an audio signal processing method.

Background Art

[0002] In a vehicle interior, for example, when one passenger makes a call from the vehicle interior to a person outside the vehicle using a mobile terminal, other passengers in the vehicle interior can hear the transmitted voice of the caller in the vehicle interior, but may feel uncomfortable because they cannot hear the received voice.

[0003] For this reason, there is a technique of collecting the transmitted voice by a microphone provided near the caller in the vehicle interior, generating an inverted-phase sound of the transmitted voice, and outputting it from a speaker provided near other passengers than the caller, thereby making the call voice less audible to the passengers (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, a caller in the vehicle interior may talk to other passengers during a call. In this case, the inverted-phase sound originally intended to suppress the discomfort of other passengers may interfere with the temporary conversation between the caller and other passengers in the vehicle interior.

[0006] One aspect of the embodiment has been made in view of the above, and an object is to provide an audio signal processing apparatus and an audio signal processing method capable of making the transmitted voice in the vehicle interior less audible to other passengers without inhibiting the temporary conversation between the caller and other passengers in the vehicle interior.

Means for Solving the Problems

[0007] An audio signal processing device according to one embodiment outputs a sound from a speaker to a passenger that makes it difficult for the voice of a caller inside the vehicle to be heard by a passenger other than the caller inside the vehicle. When the audio signal processing device detects speech from the caller to the passenger, or from the passenger to the caller, during a call, it stops outputting the sound. [Effects of the Invention]

[0008] An audio signal processing device and an audio signal processing method according to one embodiment have the effect of making the transmitted audio inside the vehicle less audible to the passenger without interfering with the temporary conversation between the person making the call inside the vehicle and the passenger. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 is an explanatory diagram showing an overview of the audio signal processing method according to an embodiment. [Figure 2] Figure 2 is a functional block diagram showing an example configuration of an audio signal processing device according to an embodiment. [Figure 3] Figure 3 is a flowchart showing an example of a process performed by the controller of the audio signal processing device according to the embodiment. [Figure 4] Figure 4 is a flowchart showing an example of a process performed by the controller of the audio signal processing device according to the embodiment. [Figure 5] Figure 5 is a flowchart showing an example of a process performed by the controller of the audio signal processing device according to the embodiment. [Modes for carrying out the invention]

[0010] Embodiments of the audio signal processing device and audio signal processing method will be described in detail below with reference to the attached drawings. However, the present invention is not limited to the embodiments described below.

[0011] [1. Overview of Audio Signal Processing Methods] First, with reference to Figure 1, an overview of the audio signal processing method performed by the audio signal processing device according to the embodiment will be described. Figure 1 is an explanatory diagram showing an overview of the audio signal processing method according to the embodiment. Here, we will describe a case where an occupant in the passenger seat of vehicle 100 is making a call with someone outside the vehicle using a mobile terminal, and the driver is seated in the driver's seat of vehicle 100.

[0012] In the following, the passenger in the front seat will be referred to as the caller 10, the person on the other end of the call outside the vehicle will be referred to as the outside caller 11, and the passenger in the driver's seat will be referred to as the passenger 12. The voice signal processing method according to this embodiment also applies when the driver of the vehicle 100 is the caller, and passengers other than the driver are passengers other than the caller. Furthermore, the voice signal processing method according to this embodiment also applies when there are multiple passengers other than the caller 10 inside the vehicle.

[0013] As shown in the upper diagram of Figure 1, the audio signal processing device 1 is connected to a microphone 20, a speaker 21, and a camera 22 installed in the vehicle 100. When a caller 10 inside the vehicle and a caller 11 outside the vehicle start a call using their mobile devices, the audio signal processing device 1 generates a sound that makes it difficult for passengers 12 other than the caller 10 inside the vehicle to hear the call audio.

[0014] For example, the audio signal processing device 1 acquires the transmitted voice of the caller 10 from the microphone 20 and generates an inverted-phase sound of the transmitted voice (hereinafter referred to as "cancellation sound"). The audio signal processing device 1 then outputs the cancellation sound from the speaker 21.

[0015] As a result, the voice signal processing device 1 can suppress the passenger 12 from becoming uncomfortable due to the voice transmitted by the caller 10, because the voice of the caller 10 cancels out the transmitted voice.

[0016] Furthermore, when a call is initiated, the audio signal processing device 1 can output a masking tone instead of a cancellation tone, or it can output both a cancellation tone and a masking tone simultaneously. The masking tone may be, for example, a natural ambient sound or background music (BGM).

[0017] After that, during a call, the caller 10 may temporarily interrupt the transmission and talk to the passenger 12. Also, during a call, the passenger 12 may talk to the caller 10. In this case, if the output of the cancellation sound or the masking sound continues, it becomes difficult for the passenger 12 to hear the voice of the caller 10.

[0018] Therefore, as shown in the lower diagram of FIG. 1, when the voice signal processing device 1 detects a speech from the caller 10 to the passenger 12 or from the passenger 12 to the caller 10 during a call, it stops the output of the cancellation sound and the masking sound. Thereby, the voice signal processing device 1 can make the transmitted voice in the vehicle interior difficult to be heard by the passenger 12 without hindering the temporary conversation between the caller 10 and the passenger 12 in the vehicle interior.

[0019] [2. Configuration example of voice signal processing device] Next, referring to FIG. 2, a configuration example of the voice signal processing device according to the embodiment will be described. FIG. 2 is a functional block diagram showing a configuration example of the voice signal processing device according to the embodiment.

[0020] As shown in FIG. 2, the voice signal processing device 1 includes a controller 2 and a storage unit 7. The storage unit 7 is, for example, an information storage device such as a data flash, and stores masking sound information 71 and passenger information 72.

[0021] The masking sound information 71 includes, for example, voice information such as natural environmental sounds or BGM (Back Ground Music). The passenger information 72 includes, for example, voiceprint information of the passengers of the vehicle 100 registered in advance, face image information of the passengers, and name information of the passengers.

[0022] Furthermore, when the caller 10 uses the hands-free calling system of the vehicle 100, the memory unit 7 stores the voiceprint information of the caller 11 outside the vehicle as user information. In this case, the controller 2 may pre-store the voiceprint information of the caller 11 outside the vehicle in the memory unit 7, or it may acquire the speech of the caller 11 outside the vehicle output from the speaker 21 during hands-free calling using the microphone 20 and store it in the memory unit 7 as the voiceprint information of the caller 11 outside the vehicle.

[0023] Controller 2 includes a microcomputer with a CPU (Central Processing Unit), ROM (Read Only Memory), RAM (Random Access Memory), and various circuits. Controller 2 includes a call detection unit 3, an audio output control unit 4, an image analysis unit 5, and an audio analysis unit 6, all of which function by the CPU executing a program stored in ROM using RAM as a working area.

[0024] Furthermore, the call detection unit 3, voice output control unit 4, image analysis unit 5, and voice analysis unit 6 of the controller 2 may be partially or entirely composed of hardware such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

[0025] The call detection unit 3, voice output control unit 4, image analysis unit 5, and voice analysis unit 6 of the controller 2 each realize or execute the information processing operations described below. Note that the internal configuration of the controller 2 is not limited to the configuration shown in Figure 2, and other configurations are also acceptable as long as they perform the information processing described later.

[0026] The call detection unit 3 detects the start and end of a call made by the caller 10. The call detection unit 3 detects the start and end of a call by analyzing at least one of the following: the sound inside the vehicle acquired by the microphone 20, the image captured by the camera 22, or the radio waves of a mobile terminal detected inside the vehicle.

[0027] Furthermore, the call detection unit 3 is connected to a mobile terminal inside the vehicle via USB (registered trademark), Bluetooth (registered trademark), or Wi-Fi (registered trademark), and when a call is initiated using the hands-free calling system, it detects the start and end of the call via USB, Bluetooth, or Wi-Fi. When the call detection unit 3 detects the start of a call, it notifies the voice output control unit 4 of this fact.

[0028] When the start of a call is notified, the voice output control unit 4 generates a cancellation tone from the transmitted voice input from the microphone 20 via the voice analysis unit 6 and outputs it through the speaker 21. At this time, the voice output control unit 4 can also read a masking tone from the masking tone information 71 in the storage unit 7 and output it through the speaker 21. Furthermore, when the end of a call is notified, the voice output control unit 4 stops outputting the cancellation tone and the masking tone.

[0029] The image analysis unit 5 analyzes images of the caller 10 and passenger 12 captured by the camera 22, and detects speech made when a specific gesture of the caller 10 or passenger 12 inside the vehicle is detected as speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10.

[0030] Specific gestures include, for example, the gesture of the caller 10 looking towards the passenger 12, the gesture of the caller 10 facing the passenger 12, the gesture of the passenger 12 looking towards the caller 10, or the gesture of the passenger 12 facing the caller 10.

[0031] Furthermore, specific gestures may include the caller 10 moving the mobile device away from their mouth while on a call, or covering the sound-receiving part of the mobile device. This allows the image analysis unit 5 to detect that the caller 10 and passenger 12 inside the vehicle may be about to start a brief conversation.

[0032] Furthermore, the call detection unit 3 detects speech when the microphone is muted or the call is put on hold during a hands-free call via USB, Bluetooth, or Wi-Fi as speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10. This allows the call detection unit 3 to detect that the caller 10 and passenger 12 inside the vehicle may be about to start a temporary conversation.

[0033] When the image analysis unit 5 and the call detection unit 3 detect speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, during a call, they notify the voice output control unit 4 of this fact. When the voice output control unit 4 is notified that speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, has been detected during a call, it stops outputting the cancellation sound and masking sound. In this way, the voice output control unit 4 can make the transmitted voice inside the vehicle less audible to the passenger 12 without interfering with the temporary conversation between the caller 10 and the passenger 12 inside the vehicle.

[0034] The voice analysis unit 6 analyzes the speech of the caller 10, which is picked up by the microphone 20, and detects that speech is spoken from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, when it contains a specific word. The specific word here is the name of the passenger 12 included in the caller 10's speech, or the name of the caller 10 included in the passenger 12's speech. This allows the voice analysis unit 6 to detect that the caller 10 and the passenger 12 inside the vehicle may be about to start a temporary conversation.

[0035] When the voice analysis unit 6 detects speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, during a call, it notifies the voice output control unit 4 of this fact.

[0036] When the voice output control unit 4 is notified that a speech has been detected between the caller 10 and the passenger 12, or between the passenger 12 and the caller 10, during a call, it stops outputting the cancellation sound and the masking sound. This allows the voice output control unit 4 to make the transmitted speech inside the vehicle less audible to the passenger 12 without interfering with the temporary conversation between the caller 10 and the passenger 12 inside the vehicle.

[0037] [3. Processes executed by the controller] Next, with reference to Figures 3 to 5, an example of processing performed by the controller of the audio signal processing device according to the embodiment will be described. Figures 3 to 5 are flowcharts showing an example of processing performed by the controller of the audio signal processing device according to the embodiment.

[0038] When a call is initiated inside the vehicle, controller 2 starts the process shown in Figure 3. As shown in Figure 3, controller 2 detects the start of a call by analyzing at least one of the following: the audio inside the vehicle acquired by microphone 20, the image captured by camera 22, or the radio waves of a mobile device detected inside the vehicle.

[0039] Furthermore, Controller 2 is connected to a mobile device inside the vehicle via USB, Bluetooth, or Wi-Fi, and detects the start of a call via USB, Bluetooth, or Wi-Fi when a call is initiated using the hands-free calling system.

[0040] When a call is initiated inside the vehicle, the controller 2 outputs at least one of a cancellation tone and a masking tone from the speaker 21 (step S101). This allows the voice signal processing device 1 to prevent the passenger 12 from being uncomfortable with the speech of the caller 10.

[0041] Next, controller 2 performs cancellation sound / masking sound output processing (step S102) and then terminates the process. When controller 2 starts cancellation sound / masking sound output processing, it first determines whether the call has ended or not, as shown in Figure 4 (step S201). Controller 2 detects the end of the call in the same way as when detecting the start of the call.

[0042] Then, if Controller 2 determines that the call has ended (Step S201, Yes), it terminates the cancellation tone / masking tone output process. If Controller 2 determines that the call has not ended (Step S201, No), it determines whether a specific gesture has occurred (Step S202).

[0043] At this time, the controller 2 analyzes the image captured by the camera 22 to determine if a specific gesture is present when the caller 10 or passenger 12 makes a specific gesture, and determines if no specific gesture is present when the caller 10 or passenger 12 does not make a specific gesture.

[0044] Specific gestures include, for example, the gesture of the caller 10 looking towards the passenger 12, the gesture of the caller 10 facing the passenger 12, the gesture of the passenger 12 looking towards the caller 10, or the gesture of the passenger 12 facing the caller 10. This allows the voice signal processing device 1 to detect that the caller 10 and the passenger 12 inside the vehicle may be having a brief conversation during the call.

[0045] Furthermore, the specific gesture may be one in which the caller 10 moves the mobile device away from their mouth while making a call, or one in which they cover the sound-receiving part of the mobile device. This also allows the audio signal processing device 1 to detect that the caller 10 and the passenger 12 inside the vehicle may be having a brief conversation.

[0046] Then, if Controller 2 determines that a specific gesture has occurred (Step S202, Yes), it determines whether or not it has detected speech from the caller 10 or the passenger 12 (Step S203). If Controller 2 determines that it has not detected speech from the caller 10 or the passenger 12 (Step S203, No), it moves the process to Step S202.

[0047] Furthermore, if the controller 2 determines that it has detected speech from the caller 10 or the passenger 12 (step S203, Yes), it stops outputting the currently outputting sound, either the cancellation sound or the masking sound (step S206). This allows the voice signal processing device 1 to make the transmitted voice inside the vehicle less audible to the passenger 12 without interfering with the temporary conversation between the caller 10 and the passenger 12 inside the vehicle.

[0048] Subsequently, controller 2 executes the process of stopping the output of the cancellation sound and masking sound (step S207), and then terminates the process of stopping the output of the cancellation sound and masking sound. A specific example of the process of stopping the output of the cancellation sound and masking sound will be described later with reference to Figure 5.

[0049] In this way, the controller 2 detects speech from the caller 10 or passenger 12 inside the vehicle as speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, when the camera 22 detects a specific gesture of the caller 10 or passenger 12 inside the vehicle. As a result, the audio signal processing device 1 can detect that the caller 10 and passenger 12 inside the vehicle may actually be starting a temporary conversation.

[0050] Then, when the controller 2 detects speech from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10, during a call, it stops outputting the cancellation sound and the masking sound that are currently being output. In this way, the audio signal processing device 1 can make the transmitted voice inside the vehicle less audible to the passenger 12 without interfering with the temporary conversation between the caller 10 and the passenger 12 inside the vehicle.

[0051] Furthermore, if controller 2 determines that there is no specific gesture (step S202, No), it determines whether or not there is a specific word in the utterance (step S204). The specific word is, for example, the name of passenger 12 included in the utterance of caller 10, or the name of caller 10 included in the utterance of passenger 12.

[0052] Then, if the controller 2 determines that a specific word is present in the utterance (step S204, Yes), it detects that specific word as an utterance from the caller 10 to the passenger 12, or from the passenger 12 to the speaker. This allows the voice signal processing device 1 to detect that the caller 10 and the passenger 12 inside the vehicle may be having a brief conversation.

[0053] Subsequently, controller 2 moves the process to step S206. Also, if controller 2 determines that there is no specific word in the utterance (step S204, No), it determines whether the microphone is muted or the call is on hold in the hands-free calling system (step S205).

[0054] Then, if the controller 2 determines that the microphone is muted or the call is on hold in the hands-free calling system (step S205, Yes), it detects the utterances of the caller 10 and passenger 12 at that time as utterances from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10. This allows the voice signal processing device 1 to detect that the caller 10 and passenger 12 inside the vehicle may be having a temporary conversation.

[0055] Subsequently, controller 2 moves the process to step S206. Also, if controller 2 determines that there is no microphone mute or call hold in the hands-free calling system (step S205, No), the process moves to step S201.

[0056] Next, with reference to Figure 5, an example of the cancellation sound / masking sound output halting process performed by the controller 2 will be described. As shown in Figure 5, when the controller 2 starts the cancellation sound / masking sound output halting process, it first determines whether the call has ended or not (step S301). The controller 2 detects the end of the call in the same way as when detecting the start of the call.

[0057] If controller 2 determines that the call has ended (step S301, Yes), it terminates the process of stopping the output of the cancellation tone / masking tone. If controller 2 determines that the call has not ended (step S301, No), it determines whether a specific gesture has occurred (step S302).

[0058] The specific gesture here is the same gesture that is determined during the cancellation sound / masking sound output processing. If controller 2 determines that the specific gesture is present (step S302, Yes), it moves the process to step S301.

[0059] Furthermore, if Controller 2 determines that there is no specific gesture (Step S302, No), it determines whether or not there is a specific word in the utterance (Step S303). The specific word here is the same word that is determined during the cancellation sound / masking sound output processing. If Controller 2 determines that there is a specific word in the utterance (Step S303, Yes), it moves the processing to Step S301.

[0060] Furthermore, if controller 2 determines that there is no specific word in the utterance (step S303, No), it determines whether to mute the microphone or put the call on hold (step S304). The microphone mute or call hold operation here is the same as the microphone mute or call hold operation determined during the cancellation sound / masking sound output processing.

[0061] If controller 2 determines that the microphone is muted or the call is on hold (step S304, Yes), it moves the process to step S301. If controller 2 determines that the microphone is not muted or the call is not on hold (step S304, No), it outputs at least one of the cancellation sound and the masking sound from speaker 21 (step S305).

[0062] Subsequently, controller 2 performs the cancellation sound / masking sound output processing (step S306). This cancellation sound / masking sound output processing is the same as the cancellation sound / masking sound output processing shown in Figure 4. After that, controller 2 terminates the cancellation sound / masking sound output stop processing.

[0063] It should be noted that the above-described embodiment is merely an example, and various modifications are possible. For example, the controller 2 may, during a call, detect the utterance of the caller 10, and then, within a predetermined time, detect the response of the passenger 12 to the utterance of the caller 10. In this case, the controller 2 may detect the passenger 12's response as an utterance from the passenger 12 to the caller 10 and stop outputting the cancellation sound and masking sound.

[0064] Furthermore, caller 10 tends to speak at a higher pitch when speaking to the person they are talking to than when speaking to passenger 12. For this reason, controller 2 may analyze caller 10's voice tone and, if caller 10's voice pitch becomes lower than the pitch at the start of the call, detect that speech from caller 10 to passenger 12 and stop outputting the cancellation and masking sounds.

[0065] Furthermore, in the above-described embodiment, the audio signal processing device 1 output a cancellation tone that is the opposite phase of the speech voice of the caller 10 inside the vehicle. However, during a call using the hands-free calling system, the device may also output a cancellation tone that is the opposite phase of the speech voice of the caller 11 outside the vehicle who is the other party to the call.

[0066] Furthermore, in the embodiment described above, the output of the cancellation sound and masking sound is stopped when a speech is detected from the caller 10 to the passenger 12, or from the passenger 12 to the caller 10. However, the output of the cancellation sound and masking sound may also be stopped when a speech is detected from a caller 11 outside the vehicle to the passenger 12, or from the passenger 12 to the caller 11 outside the vehicle.

[0067] Specifically, the controller 2 detects a conversation from the outside-vehicle caller 11 to the passenger 12 if the outside-vehicle caller 11's speech includes the passenger 12's name. Alternatively, the controller 2 detects a conversation from the passenger 12 to the outside-vehicle caller 11 if the passenger 12's speech includes the outside-vehicle caller 11's name.

[0068] When controller 2 detects a call from an outside caller 11 to a passenger 12, or from a passenger 12 to an outside caller 11, it stops outputting cancellation or masking sounds.

[0069] For example, when a caller 10 inside the car and a caller 11 outside the car are talking using a hands-free calling system, a passenger 12 who is listening to the call may speak to the caller 11 outside the car who is on the other end of the call with the caller 10 inside the car, or the caller 11 outside the car may speak to the passenger 12 who is likely to be near the caller 10 inside the car.

[0070] In such cases, it is expected that a conversation will occur between the caller 11 outside the vehicle and the passenger 12. Therefore, by stopping the output of cancellation or masking sounds, it is possible to avoid interfering with the conversation between the caller 11 outside the vehicle and the passenger 12.

[0071] Further effects and modifications can be readily derived by those skilled in the art. Therefore, broader aspects of the present invention are not limited to the specific details and representative embodiments expressed and described above. Accordingly, various modifications are possible without departing from the spirit or scope of the overall concept of the invention as defined by the appended claims and their equivalents. [Explanation of Symbols]

[0072] 1. Audio signal processing device 2 Controllers 3. Call detection unit 4. Audio Output Control Unit 5 Image Analysis Unit 6. Voice Analysis Unit 7 Memory section 10 callers 11. People making calls outside the vehicle 12 Passengers 20 microphones 21 speakers 22 cameras 71 Masking Sound Information 72 Crew Information 100 vehicles

Claims

1. The system outputs a sound through the speaker to the passengers that makes it difficult for other passengers to hear the conversation audio of the person making the call inside the vehicle. If the system detects speech from the caller to the passenger, or from the passenger to the caller, during a call, it stops the output of the sound. Audio signal processing device.

2. The system detects speech made when a specific gesture of the caller or passenger is detected by the camera, and this speech is detected as speech from the caller to the passenger, or from the passenger to the caller. The audio signal processing device according to claim 1.

3. The aforementioned specific gesture is, The gesture of the caller looking towards the passenger, the gesture of the caller facing the passenger, the gesture of the passenger looking towards the caller, or the gesture of the passenger facing the caller. The audio signal processing device according to claim 2.

4. The aforementioned specific gesture is, The gesture of the caller moving the mobile device away from their mouth while on a call, or covering the sound-receiving part of the mobile device, The audio signal processing device according to claim 2.

5. When an utterance contains a specific word, the utterance is detected as an utterance from the caller to the passenger, or from the passenger to the caller. The audio signal processing device according to claim 1.

6. The aforementioned specific word is, The name of the passenger included in the utterance of the caller, or the name of the caller included in the utterance of the passenger. The audio signal processing device according to claim 5.

7. During a call using a hands-free calling system, if the microphone is muted or the call is put on hold, the system detects this as speech from the caller to the passenger, or from the passenger to the caller. The audio signal processing device according to claim 1.

8. The audio signal processing unit The system outputs a sound through the speaker to the passengers that makes it difficult for other passengers to hear the conversation audio of the person making the call inside the vehicle. If the system detects speech from the caller to the passenger, or from the passenger to the caller, during a call, it stops the output of the sound. Audio signal processing method.

Images